Python gTTS – Word document text to speech

In todays post we will be making use of the gTTS Python library which is a tool to interface with Google translates text-to-speech API. The script will take a Word document file as input and then convert its text to speech. The audio will be saved as an MP3 file.

We begin by enabling the user to browse to a file for user input, to do this we shall use tkinter.

from tkinter import Tk     
from tkinter.filedialog import askopenfilename

Tk().withdraw() 
filename = askopenfilename() 

We then make use of the docx library to retrieve all text from our specified Word document.

import docx

def getText(filename):
    doc = docx.Document(filename)
    fullText = []
    for para in doc.paragraphs:
        fullText.append(para.text)
    return '\n'.join(fullText)

Finally we pass the text over to the gTTS module for conversion. We have also the ‘slow= False’ which should stop the playback from being slowed down.

from gtts import gTTS

tts = gTTS(Text, slow=False)
tts.save('Output.mp3')

The full source code for this project can be found below.

from tkinter import Tk     
from tkinter.filedialog import askopenfilename
from gtts import gTTS
import docx

def getText(filename):
    doc = docx.Document(filename)
    fullText = []
    for para in doc.paragraphs:
        fullText.append(para.text)
    return '\n'.join(fullText)

Tk().withdraw() 
filename = askopenfilename() 
Text = getText(filename)

tts = gTTS(Text, slow=False)
tts.save('Output.mp3')